|
I am a postdoctoral fellow at the University of Alberta working with Prof. Michael Bowling and Prof. Matthew E. Taylor. Before joining UoA, I was a postdoctoral researcher at Meta AI Research working with Prof. Abhinav Gupta. I received my PhD in Computer Science from the Technical University of Darmstadt working with Prof. Jan Peters, and my MSc degree in Computer Science Engineering from the Polytechnic University of Milan under the supervision of Prof. Marcello Restelli. My research interests lie in the area of reinforcement learning, especially in the fields of exploration, representation learning, transfer learning, policy search, and multi-objective optimization. Recently, I have been working on learning under partial observability and on methods that move away from the classic tabula-rasa paradigm towards a more practical transfer framework. More specifically, I am interested in (1) better understanding state representation learning from rich and diverse inputs, (2) developing task-agnostic exploration policies, and (3) developing policy architectures for transfer/continual learning of state representations and exploration policies. You can find more details about my research here. |
Selected Papers
Beyond Optimism: Exploration With Partially Observable Rewards
Monitored Markov Decision Processes
The (Un)Surprising Effectiveness of Pre-Trained Vision Models for Control
Long-Term Visitation Value for Deep Exploration in Sparse Reward Reinforcement Learning
Interesting Object, Curious Agent: Learning Task-Agnostic Exploration
TD-Regularized Actor-Critic Methods
Multi-objective Reinforcement Learning through Continuous Pareto Manifold Approximation
Reinforcement Learning vs Human Programming in Tetherball Robot Games |